Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bringing
    -0.07
     COM
    -0.06
     campus
    -0.06
    -command
    -0.06
    ารย
    -0.06
    scheme
    -0.06
     brought
    -0.06
    008
    -0.06
     Guild
    -0.06
    рім
    -0.06
    POSITIVE LOGITS
    CharacterSet
    0.07
     usability
    0.07
    adge
    0.07
     千
    0.06
    ProgressHUD
    0.06
    .tm
    0.06
     paar
    0.06
     stickers
    0.06
    Strange
    0.06
     Cherry
    0.06
    Act Density 0.000%

    No Known Activations